# HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation

arXiv: https://arxiv.org/abs/2608.06791 · HTML: https://mlsanity.com/paper/2608.06791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [AutoDSE: Enabling Software Programmers to Design Efficient FPGA Accelerators](https://mlsanity.com/paper/2009.14381/) (2020)
- [HLSPilot: LLM-based High-Level Synthesis](https://mlsanity.com/paper/2408.06810/) (2024)
- [ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation](https://mlsanity.com/paper/2107.11673/) (2021)
- [C2HLSC: Leveraging Large Language Models to Bridge the Software-to-Hardware Design Gap](https://mlsanity.com/paper/2412.00214/) (2024)
- [Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis](https://mlsanity.com/paper/2502.13921/) (2025)
- [HLS-Eval: A Benchmark and Framework for Evaluating LLMs on High-Level Synthesis Design Tasks](https://mlsanity.com/paper/2504.12268/) (2025)
- [HLSFactory: A Framework Empowering High-Level Synthesis Datasets for Machine Learning and Beyond](https://mlsanity.com/paper/2405.00820/) (2024)
- [LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning](https://mlsanity.com/paper/2504.21187/) (2025)
- [Optimizing High-Level Synthesis Designs with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2410.07356/) (2024)
- [ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis](https://mlsanity.com/paper/2507.00642/) (2025)
- [A Unified Framework for Automated Code Transformation and Pragma Insertion](https://mlsanity.com/paper/2405.03058/) (2024)
- [TimelyHLS: LLM-Based Timing-Aware and Architecture-Specific FPGA HLS Optimization](https://mlsanity.com/paper/2507.17962/) (2025)
- [AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance](https://mlsanity.com/paper/2606.30949/) (2026)
- [Best-Effort FPGA Programming: A Few Steps Can Go a Long Way](https://mlsanity.com/paper/1807.01340/) (2018)
- [LAAFD: LLM-based Agents for Accelerated FPGA Design](https://mlsanity.com/paper/2602.06085/) (2026)
- [Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?](https://mlsanity.com/paper/2603.25719/) (2026)
- [CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs](https://mlsanity.com/paper/2605.08467/) (2026)
- [HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning](https://mlsanity.com/paper/2605.13536/) (2026)

## Abstract (arXiv)

Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large language models (LLMs) have demonstrated strong software-generation capabilities, even frontier models lack the hardware intuition and procedural knowledge needed to reliably translate baseline C/C++ programs into high-performance HLS designs: they struggle to identify effective architectures, follow the optimization processes used by HLS experts, and apply hardware transformations consistently across diverse kernels. We present HLSmith, an expert-guided framework for translating C/C++ programs into optimized HLS accelerators. HLSmith combines three components: an HLS optimization expertise library that encodes guarded transformation recipes, their applicability and prerequisite conditions, and unsafe cases to avoid; a staged, feedback-driven orchestration flow modeled on expert HLS development practice that guides agents through synthesis, bottleneck analysis, and optimization; and a tool-grounded model-adaptation pipeline that converts optimization trajectories from commercial frontier models into training data for fine-tuning open-weight LLMs. We evaluate HLSmith on PolyBench against ChatHLS, a leading prior agent-orchestration framework for HLS accelerator development. HLSmith achieves a geometric mean speedup of 4.24x over ChatHLS while producing functionally correct designs, in both software and RTL simulation, for every benchmark, compared with ChatHLS's 57% valid-design rate. It further reaches speedups of up to 252x and 138x with commercial frontier models and open-weight models, respectively.